Training in progress, epoch 1

README.md

@@ -1,24 +1,25 @@
 ---
+library_name: transformers
 license: mit
-base_model: roberta-base
+base_model: roberta-large
 tags:
 - generated_from_trainer
 model-index:
-- name: psychopathy_continuous
+- name: machiavellianism_continuous
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# psychopathy_continuous
+# machiavellianism_continuous
 
-This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
+This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0542
-- Rmse: 0.2327
-- Mae: 0.1859
-- Corr: 0.4767
+- Loss: 0.0575
+- Rmse: 0.2398
+- Mae: 0.1972
+- Corr: 0.4360
 
 ## Model description
 
@@ -49,13 +50,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rmse   | Mae    | Corr   |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|
-| No log        | 1.0   | 267  | 0.0546          | 0.2336 | 0.1890 | 0.4683 |
-| 0.0612        | 2.0   | 534  | 0.0542          | 0.2327 | 0.1859 | 0.4767 |
+| No log        | 1.0   | 267  | 0.0589          | 0.2426 | 0.1975 | 0.4210 |
+| 0.0805        | 2.0   | 534  | 0.0575          | 0.2398 | 0.1972 | 0.4360 |
 
 
 ### Framework versions
 
-- Transformers 4.43.3
-- Pytorch 2.4.0
-- Datasets 2.20.0
+- Transformers 4.44.1
+- Pytorch 1.11.0
+- Datasets 2.12.0
 - Tokenizers 0.19.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "roberta-base",
+  "_name_or_path": "roberta-large",
   "architectures": [
     "RobertaForSequenceClassification"
   ],
@@ -9,25 +9,25 @@
   "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "LABEL_0"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "LABEL_0": 0
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "regression",
   "torch_dtype": "float32",
-  "transformers_version": "4.43.3",
+  "transformers_version": "4.44.1",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50265

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c476461331a8abafa1c80533bc6886fbb4d54c9f79a6c18ce0527b43281d5d51
-size 498609748
+oid sha256:9697aadae9a32d636fb8542337a0fd93a0dd4eb320e3714a6d7fd8e523612b50
+size 1421491316

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7fea53418f92f13f2f19f6c1042e480add534666e3d94571c136001f0ad0d1
-size 5240
+oid sha256:4bafd8d962a3a46ee8f6d8f37d0cb54d0984f363898b872c0d79f7f4cad90fef
+size 4719